CUEBES

Traces of Social Competence in Large Language Models

arXiv:2603.04161v1 Announce Type: new Abstract: The False Belief Test (FBT) has been the main method for assessing Theory of Mind (ToM) and related socio-cognitive competencies....

Neuroscience Psychology

arXiv CS Mar 5

Bielik-Q2-Sharp: A Comparative Study of Extreme 2-bit Quantization Methods for a Polish 11B Language Model

arXiv:2603.04162v1 Announce Type: new Abstract: We present Bielik-Q2-Sharp, the first systematic academic evaluation of extreme 2-bit quantization applied to a Polish large language model. Using...

Software Policy

arXiv CS Mar 5

Degradation-based augmented training for robust individual animal re-identification

arXiv:2603.04163v1 Announce Type: new Abstract: Wildlife re-identification aims to recognise individual animals by matching query images to a database of previously identified individuals, based on...

Software World News

arXiv CS Mar 5

PlaneCycle: Training-Free 2D-to-3D Lifting of Foundation Models Without Adapters

arXiv:2603.04165v1 Announce Type: new Abstract: Large-scale 2D foundation models exhibit strong transferable representations, yet extending them to 3D volumetric data typically requires retraining, adapters, or...

Software Engineering

arXiv CS Mar 5

Learning Hip Exoskeleton Control Policy via Predictive Neuromusculoskeletal Simulation

arXiv:2603.04166v1 Announce Type: new Abstract: Developing exoskeleton controllers that generalize across diverse locomotor conditions typically requires extensive motion-capture data and biomechanical labeling, limiting scalability beyond...

Hardware Policy

arXiv CS Mar 5

OMNIINTENT: A Trusted Intent-Centric Framework for User-Friendly Web3

arXiv:2603.04168v1 Announce Type: new Abstract: The increasingly complex Web3 ecosystem and decentralized finance (DeFi) landscape demand ever higher levels of technical expertise and financial literacy...

Environment Finance

arXiv CS Mar 5

Efficient Query Rewrite Rule Discovery via Standardized Enumeration and Learning-to-Rank

arXiv:2603.04169v1 Announce Type: new Abstract: Query rewriting is essential for database performance optimization, but existing automated rule enumeration methods suffer from exponential search spaces, severe...

Engineering Software

arXiv CS Mar 5

Scalable Join Inference for Large Context Graphs

arXiv:2603.04176v1 Announce Type: new Abstract: Context graphs are essential for modern AI applications including question answering, pattern discovery, and data analysis. Building accurate context graphs...

Software Artificial Intelligence

arXiv CS Mar 5

CodeTaste: Can LLMs Generate Human-Level Code Refactorings?

arXiv:2603.04177v1 Announce Type: new Abstract: Large language model (LLM) coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt....

Psychology Software

arXiv CS Mar 5

NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction

arXiv:2603.04179v1 Announce Type: new Abstract: We present NOVA3R, an effective approach for non-pixel-aligned 3D reconstruction from a set of unposed images in a feed-forward manner....

Software Energy

arXiv CS Mar 5

Architectural Proprioception in State Space Models: Thermodynamic Training Induces Anticipatory Halt Detection

arXiv:2603.04180v1 Announce Type: new Abstract: We introduce the Probability Navigation Architecture (PNA) framework, which treats neural computation as navigation through a probability manifold governed by...

Psychology Neuroscience

arXiv CS Mar 5

REDNET-ML: A Multi-Sensor Machine Learning Pipeline for Harmful Algal Bloom Risk Detection Along the Omani Coast

arXiv:2603.04181v1 Announce Type: new Abstract: Harmful algal blooms (HABs) can threaten coastal infrastructure, fisheries, and desalination dependent water supplies. This project (REDNET-ML) develops a reproducible...

Space & Astronomy Energy

arXiv CS Mar 5

CAM-LDS: Cyber Attack Manifestations for Automatic Interpretation of System Logs and Security Alerts

arXiv:2603.04186v1 Announce Type: new Abstract: Log data are essential for intrusion detection and forensic investigations. However, manual log analysis is tedious due to high data...

Engineering Cybersecurity

arXiv CS Mar 5

Enhancing Power Systems Transmission Adequacy via Optimal BESS Siting and Sizing using Benders Decomposition with Feasibility Cuts

arXiv:2603.04189v1 Announce Type: new Abstract: This work presents a general framework for the operationally driven optimal siting and sizing of battery energy storage systems in...

Energy Policy

arXiv CS Mar 5

Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions

arXiv:2603.04191v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly serving as personal assistants, where users share complex and diverse preferences over extended interactions....

Software Policy

arXiv CS Mar 5

Noise-aware Client Selection for carbon-efficient Federated Learning via Gradient Norm Thresholding

arXiv:2603.04194v1 Announce Type: new Abstract: Training large-scale Neural Networks requires substantial computational power and energy. Federated Learning enables distributed model training across geospatially distributed data...

Energy Artificial Intelligence

arXiv CS Mar 5

Security-Constrained Substation Reconfiguration Considering Busbar and Coupler Contingencies

arXiv:2603.04203v1 Announce Type: new Abstract: Substation reconfiguration via busbar splitting can mitigate transmission grid congestion and reduce operational costs. However, existing approaches neglect the security...

Software Cybersecurity

arXiv CS Mar 5

Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild

arXiv:2603.04205v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world...

Technology Software

arXiv CS Mar 5

GSeg3D: A High-Precision Grid-Based Algorithm for Safety-Critical Ground Segmentation in LiDAR Point Clouds

arXiv:2603.04208v1 Announce Type: new Abstract: Ground segmentation in point cloud data is the process of separating ground points from non-ground points. This task is fundamental...

Robotics Environment

arXiv CS Mar 5

Beyond Edge Deletion: A Comprehensive Approach to Counterfactual Explanation in Graph Neural Networks

arXiv:2603.04209v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are increasingly adopted across domains such as molecular biology and social network analysis, yet their black-box...

Software Technology

arXiv CS Mar 5

Code Fingerprints: Disentangled Attribution of LLM-Generated Code

arXiv:2603.04212v1 Announce Type: new Abstract: The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale....

Engineering Software

arXiv CS Mar 5

Statistical Topological Gradient and Shape Optimization for Robust Metal--Semiconductor Contact Reconstruction

arXiv:2603.04216v1 Announce Type: new Abstract: We develop a statistically robust framework for reconstructing metal--semiconductor contact regions using topological gradients. The inverse problem is formulated as...

Materials Science Engineering

arXiv CS Mar 5

When Do Language Models Endorse Limitations on Human Rights Principles?

arXiv:2603.04217v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly mediate global information access with the potential to shape public discourse, their alignment with...

Economics Engineering

arXiv CS Mar 5

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

arXiv:2603.04219v1 Announce Type: new Abstract: We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic...

Chemistry Software